Recent video-language models have shown great potential for video understanding, but still struggle with accurate temporal grounding for event-level perception. We observe that two main factors in video understanding (i.e., temporal grounding and textual response) form a logical hierarchy: accurate temporal evidence grounding lays the foundation for reliable textual response. However, existing works typically handle these two tasks in a coupled manner without a clear logical structure, leading to sub-optimal objectives. We address this from a factorized learning perspective. We first propose D$^2$VLM, a framework that decouples the learning of these two tasks while also emphasizing their inherent dependency. We adopt a "grounding then answering with evidence referencing" paradigm and introduce evidence tokens for evidence grounding, which emphasize event-level visual semantic capture beyond the focus on timestamp representation in existing works. To further facilitate the learning of these two tasks, we introduce a novel factorized preference optimization (FPO) algorithm. Unlike standard preference optimization, FPO explicitly incorporates probabilistic temporal grounding modeling into the optimization objective, enabling preference learning for both temporal grounding and textual response. We also construct a synthetic dataset to address the lack of suitable datasets for factorized preference learning with explicit temporal grounding. Experiments on various tasks demonstrate the clear advantage of our approach. Our source code is available at https://github.com/nusnlp/d2vlm.
SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding
Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB)（电子、信息与生物工程系）；Politecnico di Milano（米兰理工大学）；IRCCS Humanitas Research Hospital（IRCCS人类itas研究医院）；UCL Hawkes Institute and Department of Computer Science（UCL Hawkes研究所和计算机科学系）；University College London（伦敦大学学院）；University of Manchester（曼彻斯特大学）
Towards Temporal Compositional Reasoning in Long-Form Sports Videos
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS）
MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph
Mohamed bin Zayed University of Artificial Intelligence（莫扎德大学人工智能学院）；University of Chinese Academy of Sciences（中国科学院大学）；Kyoto University（京都大学）；Tsinghua University（清华大学）；East China Normal University（华东师范大学）；Center for Excellence in Brain Science and Intelligence Technology（脑科学与智能技术卓越中心）；Brigham and Women’s Hospital, Harvard Medical School（哈佛医学院布里特妇女医院）；GenBio AI
AlphaRAD: Grounded Zero-Shot Classification in Chest Radiology via $α$-Corrected Binary Cross Entropy and Factorized Latent Supervision
Peter Munk Cardiac Centre, University Health Network (UHN)（彼得·芒克心脏中心，大学健康网络（UHN））；Ted Rogers Centre for Heart Research（泰德·罗杰斯心脏研究中心）；University of Toronto (U of T)（多伦多大学）；Vector Institute（向量研究所）；Toronto General Hospital Research Institute, UHN（多伦多总医院研究所，大学健康网络（UHN））
MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded Framework for Hypothesis Generation in Chemistry
Stevens Institute of Technology（史蒂文斯理工学院）；University of British Columbia（不列颠哥伦比亚大学）；University of Maryland（马里兰大学）；Artificial Intelligence Interdisciplinary Institute at Maryland（马里兰人工智能跨学科研究所）
MedScope: Incentivizing "Think with Videos" for Clinical Reasoning via Coarse-to-Fine Tool Calling
College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China（上海交通大学医学院健康科学与技术学院）；Fudan University, Shanghai, China（复旦大学）；Shanghai Innovation Institute, Shanghai, China（上海创新研究院）；Tsinghua University, Beijing, China（清华大学）；Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室）；The Chinese University of Hong Kong, Hong Kong, China（香港中文大学）；Ruijin Hospital, Shanghai Jiaotong University, Shanghai, China（上海交通大学瑞金医院）
Efficient video action recognition remains a challenging problem. One large model after another takes the place of the state-of-the-art on the Kinetics dataset, but real-world efficiency evaluations are often lacking. In this work, we fill this gap and investigate the use of transformers for efficient action recognition. We propose a novel, lightweight action recognition architecture, VideoLightFormer. In a factorized fashion, we carefully extend the 2D convolutional Temporal Segment Network with transformers, while maintaining spatial and temporal video structure throughout the entire model. …
CHRONOBERG: Capturing Language Evolution and Temporal Awareness in Foundation Models
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Department of Computer Science and Mathematics, University of Bremen（不莱梅大学计算机科学与数学系）；Hessian Center for AI (hessian.AI)（黑森人工智能中心）；Department of Computer Science, TU Darmstadt（图宾根大学计算机科学系）；Centre for Cognitive Science, TU Darmstadt（图宾根大学认知科学中心）；CERTAIN
MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Department of Electrical and Computer Engineering, Carnegie Mellon University（卡内基梅隆大学电气与计算机工程系）
University of Amsterdam（阿姆斯特丹大学）；Mercedes-Benz（梅赛德斯-奔驰）
Graph neural networks have shown to learn effective node representations, enabling node-, link-, and graph-level inference. Conventional graph networks assume static relations between nodes, while relations between entities in a video often evolve over time, with nodes entering and exiting dynamically. In such temporally-dynamic graphs, a core problem is inferring the future state of spatio-temporal edges, which can constitute multiple types of relations. To address this problem, we propose MTD-GNN, a graph network for predicting temporally-dynamic edges for multiple types of relations. We pro…
Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague（布拉格捷克理工大学捷克信息学、机器人学与控制论研究所）；Inria, École normale supérieure, CNRS, PSL Research University（法国国家信息与自动化研究所、巴黎高等师范学院、法国国家科学研究中心、PSL大学）
本文提出了grounded video caption generation新任务，构建了GROC测试集和HowToGround训练集，并开发了VideoGround模型，通过统一视频字幕生成与目标定位，在时间一致的边界框基础上实现了该任务的最新技术水平。
DENSE: Longitudinal Progress Note Generation with Temporal Modeling of Heterogeneous Clinical Notes Across Hospital Visits
Department of Computer Science and Information Systems, Birla Institute of Technology and Science, Pilani, Hyderabad Campus（计算机科学与信息系统系，比拉理工学院，比拉理工学院，海得拉巴校区）
Large-scale Pre-training for Grounded Video Caption Generation
Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague（捷克信息技术、机器人与自动化研究所（捷克技术大学））；Inria, École normale supérieure, CNRS, PSL Research University（法国国家信息与自动化研究所、法国高等师范学校、法国国家科学研究中心、巴黎-萨克勒大学）
When Do LLMs Apply the Wrong Law? Diagnosing LLM Failures in Temporal Legal Reasoning
Institute of Science Tokyo（东京科学大学）；Osaka University（大阪大学）；NII LLMC（日本信息学研究所语言、语言学与媒体中心）；Nara Institute of Science and Technology（奈良科学技术研究所）；Center of Juris-Informatics, ROIS-DS（日本学术研究推进机构跨学科科学研究中心法学信息学中心）
HeiCo-FOCUS: A Clinically Grounded Dataset for Long-Context Video Understanding
German Cancer Research Center (DKFZ) Heidelberg（德国癌症研究中心（DKFZ）海德堡）；Heidelberg University（海德堡大学）；National Center for Tumor Diseases (NCT)（国家肿瘤疾病中心（NCT））；Helmholtz Imaging（亥姆霍兹影像）；Stanford University（斯坦福大学）；University of Pennsylvania（宾夕法尼亚大学）
GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking
Queen Mary University of London（伦敦玛丽女王大学）；Samsung AI Centre Cambridge（剑桥三星人工智能中心）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Nanyang Technological University（南洋理工大学）
